The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Switch to timm RmsNorm to avoid gap w/ old PyTorch versions that timm still supports
R
Ross Wightman committed
b293674ec53a81b554bfaf27c9fc52638bb601a4
Parent: f7419a3
Committed by Ross Wightman <rwightman@users.noreply.github.com>
on 4/23/2026, 5:26:34 AM